Face #ID shown #unlocking for #family #members who aren’t #alike

Apple’s Face ID is the safest facial recognition system ever made for smartphones. Unlike its Android alternatives, it can’t be hacked with photos, and it can be used to authenticate mobile payments. It’s a lot more secure than Touch ID, and it’ll likely equip more Apple devices in the future. Even Android device makers are expected to copy Face ID this year.

But Face ID isn’t hackproof. It’s been proven already that young children can hack into their parents’ iPhone X units. Twins and triplets can also unlock the phones belonging to their siblings, especially at young age, and it’s pretty obvious why that happens.

A brand new video shows the same kind of Face ID hack between two family members who aren’t alike.

Posted on YouTube, a short video clip shows a daughter and mother unlocking the same iPhone using Face ID. The daughter isn’t that young, and she’s not so similar to her mother.

The Face ID hack is successful time and again, which is impressive. Somehow, the device thinks the same person is facing the phone, and it’s unlocking the device accordingly.

It’s unclear at this time whether the iPhone was trained to recognize both family members. The way Face ID works is that it keeps taking images of the user whenever the phone is unlocked, to continuously update the mathematical expression assigned to one’s face. By inputting the password after a failed Face ID unlock, you practically instruct the phone to include the most recent scan in its library, especially if it somewhat matches your face. Is this a real hack? Or is it a sort of error where Face ID was simply trained to recognize both faces, and made up some sort of weird mix between the two? After all, the two women are still mother and daughter, so it’s likely Face ID can find more than a few similarities between them.

Here’s a reminder of how Face ID works:

To improve unlock performance and keep pace with the natural changes of your face and look, Face ID augments its stored mathematical representation over time. Upon successful unlock, Face ID may use the newly calculated mathematical representation—if its quality is sufficient—for a finite number of additional unlocks before that data is discarded. Conversely, if Face ID fails to recognize you, but the match quality is higher than a certain threshold and you immediately follow the failure by entering your passcode, Face ID takes another capture and augments its enrolled Face ID data with the newly calculated mathematical representation. This new Face ID data is discarded after a finite number of unlocks and if you stop matching against it. These augmentation processes allow Face ID to keep up with dramatic changes in your facial hair or makeup use, while minimizing false acceptance.

Whatever is allowing this hack to work, Apple should definitely find a way to fix it.